TurkerNeXtV2: An Innovative CNN Model for Knee Osteoarthritis Pressure Image Classification

TL;DR

TurkerNeXtV2 is a lightweight CNN model designed for medical imaging that achieves high accuracy and fast performance in classifying knee osteoarthritis pressure images.

Contribution

The paper introduces TurkerNeXtV2, a compact CNN with a novel pooling-based attention block and hybrid downsampling module for efficient medical image classification.

Findings

TurkerNeXtV2 achieved 87.77% validation accuracy on Stable ImageNet-1k during pretraining.

The model reached 93.40% accuracy on the knee osteoarthritis test set with high precision and recall.

It processed images at 128.8 images per second, outperforming transformer baselines in speed.

Abstract

Background/Objectives: Lightweight CNNs for medical imaging remain limited. We propose TurkerNeXtV2, a compact CNN that introduces two new blocks: a pooling-based attention with an inverted bottleneck (TNV2) and a hybrid downsampling module. These blocks improve stability and efficiency. The aim is to achieve transformer-level effectiveness while keeping the simplicity, low computational cost, and deployability of CNNs. Methods: The model was first pretrained on the Stable ImageNet-1k benchmark and then fine-tuned on a collected plantar-pressure OA dataset. We also evaluated the model on a public blood-cell image dataset. Performance was measured by accuracy, precision, recall, and F1-score. Inference time (images per second) was recorded on an RTX 5080 GPU. Grad-CAM was used for qualitative explainability. Results: During pretraining on Stable ImageNet-1k, the model reached a validation accuracy of 87.77%. On the OA test set, the model achieved 93.40% accuracy (95% CI: 91.3–95.2%) with balanced precision and recall above 90%. On the blood-cell dataset, the test accuracy was 98.52%. The average inference time was 0.0078 s per image (≈128.8 images/s), which is comparable to strong CNN baselines and faster than the transformer baselines tested under the same settings. Conclusions: TurkerNeXtV2 delivers high accuracy with low computational cost. The pooling-based attention (TNV2) and the hybrid downsampling enable a lightweight yet effective design. The model is suitable for real-time and clinical use. Future work will include multi-center validation and broader tests across imaging modalities.

Figures